Localized Uncertainty Attacks

Abstract

The susceptibility of deep learning models to adversarial perturbations has stirred renewed attention in adversarial examples resulting in a number of attacks. However, most of these attacks fail to encompass a large spectrum of adversarial perturbations that are imperceptible to humans. In this paper, we present localized uncertainty attacks, a novel class of threat models against deterministic and stochastic classifiers. Under this threat model, we create adversarial examples by perturbing only regions in the inputs where a classifier is uncertain. To find such regions, we utilize the predictive uncertainty of the classifier when the classifier is stochastic or, we learn a surrogate model to amortize the uncertainty when it is deterministic. Unlike ${\ell }_p$ ball or functional attacks which perturb inputs indiscriminately, our targeted changes can be less perceptible. When considered under our threat model, these attacks still produce strong adversarial examples; with the examples retaining a greater degree of similarity with the inputs.

arXiv commentCVPR 2021 Workshop on Adversarial Machine Learning in Computer Vision

References in corpus (17)

• Language Models are Few-Shot Learners
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
• Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
• Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
• The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
• Provable defenses against adversarial examples via the convex outer adversarial polytope
• Understanding Measures of Uncertainty for Adversarial Example Detection
• On Adversarial Examples for Character-Level Neural Machine Translation
• Unrestricted Adversarial Examples via Semantic Manipulation
• Adversarial Examples in Modern Machine Learning: A Review
• Learning perturbation sets for robust machine learning
• On the Geometry of Adversarial Examples
• Confidence-Calibrated Adversarial Training: Generalizing to Unseen Attacks
• Quantifying Perceptual Distortion of Adversarial Examples
• Robustness of Bayesian Neural Networks to Gradient-Based Attacks
• On Certifying Non-uniform Bound against Adversarial Attacks
• Semantics Preserving Adversarial Learning